The US Defense Advanced Research Projects Agency (DARPA) is seeking proposals to automate air-to-air combat as part of its Air Combat Evolution (ACE) programme.
Automating air-to-air combat will enable pilots to focus their resources on the larger air battle, according to the agency.
DARPA is keen on turning aerial dogfighting over to AI as it hopes the technology will be able to handle a high-end fight, elevating the pilot’s role to cockpit-based mission commander.
ACE programme will initially focus on increasing the trust of troops in autonomous combat technology by promoting human-machine collaborative dogfighting.
As part of this, a Proposers Day will be held later this month to move forward with its efforts to tap artificial intelligence (AI) to develop autonomous air-to-air combat capabilities.
To be held in Arlington, Virginia, the Proposers Day will reach out to interested researchers.
DARPA Strategic Technology Office (STO) ACE programme manager airforce lieutenant colonel Dan Javorsek said: “Being able to trust autonomy is critical as we move toward a future of warfare involving manned platforms fighting alongside unmanned systems.
“We envision a future in which AI handles the split-second manoeuvring during within-visual-range dogfights, keeping pilots safer and more effective as they orchestrate large numbers of unmanned systems into a web of overwhelming combat effects.”
Through ACE, the agency aims to shift combat concepts to a mix of manned and cost-effective unmanned systems.
Known as ‘mosaic warfare’, this approach involves linking manned aircraft together with inexpensive unmanned systems to fight the combat.
It will enable the forces to easily recompose the individual ‘pieces’ to create different effects or quickly replaced if destroyed.
As part of the programme, AI technologies will be trained in aerial dogfighting in a manner similar to how new pilots are trained.
The training will include basic fighter manoeuvres in simple, one-on-one scenarios. If pilots are satisfied with the reliability of the AI algorithms in handling bounded, transparent and predictable behaviours, the training will proceed to more complex aerial engagement scenarios.
Javorsek added: “Following virtual testing, we plan to demonstrate the dogfighting algorithms on sub-scale aircraft leading ultimately to live, full-scale manned-unmanned team dogfighting with operationally representative aircraft.”